comment-sentiment-action-cards
Pass
Audited by Gen Agent Trust Hub on Jun 13, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The execution script (
scripts/run.py) implements standard security measures, including the use of environment variables for API key management and standard SSL certificate verification through thecertifilibrary. - [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection attack surface as it is designed to ingest and process untrusted external data.
- Ingestion points: Data enters the agent context through the
commentCorpusText,commentExportFile, andcommentSourceLinkfields defined inreferences/form-schema.json. - Boundary markers: There are no explicit boundary markers or instructions to the agent to disregard embedded commands within the ingested data in the provided configuration.
- Capability inventory: The skill's capabilities are limited to network communication with its designated API endpoint (
ai-skills.ai) for task execution. - Sanitization: No input validation or sanitization is evidenced in the skill's manifest or reference files for the processed content.
Audit Metadata